sayan — LessWrong

LESSWRONG
LW

sayan — LessWrong

Replying toThe Hierarchy of Memory Reconsolidation Techniques

The Hierarchy of Memory Reconsolidation Techniques

Enjoyed reading this. Looking forward to the next posts in the sequence.

sayan6yQuick Take

Are Dharma traditions that posit 'innate moral perfection of everyone by default' reasoning from the just world fallacy?

sayan6yQuick Take

Can we have a market with qualitatively different (un-interconvertible) forms of money?

sayan6yQuick Take

How would signalling/countersignalling work in a post-scarcity economy?

sayan6yQuick Take

What are some effective ways to reset the hedonic baseline?

Replying toValue Impact

sayan6y

Value Impact

As far as I understand, this post decomoses 'impact' into value impact and objective impact. VI is dependent on some agent's ability to reach arbitrary value-driven goals, while OI depends on any agent's ability to reach goals in general.

I'm not sure if there exists a robust distinction between the two - the post doesn't discuss any general demarcation tool.

Maybe I'm wrong, but I think the most important point to note here is that 'objectiveness' of an impact is defined not to be about the 'objective state of the world' - rather about how 'general to all agents' an impact is.

Replying toReframing Impact

sayan6y

Reframing Impact

I think this post is broadly making two claims -

Impactful things fundamentally feel different.
A good Impact Measure should be designed in a way that it strongly safeguards against almost any imperfect objective.

It is also (maybe implicitly) claiming that the three properties mentioned completely specify a good impact measure.

I am looking forward to reading the rest of the sequence with arguments supporting these claims.

sayan6yQuick Take

What gadgets have improved your productivity?

For example, I started using a stylus few days ago and realized it can be a great tool for a lot of things!

I am thinking about these questions about a lot without actually reaching anywhere.

What is the nature of non-dual epistemology? What does it mean to 'reason' from the (Intentional Stance)[https://en.wikipedia.org/wiki/Intentional_stance], from inside of an agent?

sayan6y

Seems like this has been done already.

https://www.alignmentforum.org/posts/yXPT4nr4as7JvxLQa/classifying-specification-problems-as-variants-of-goodhart-s

If there is no self, what are we going to upload to the cloud?

It is so difficult to understand the difference and articulate in pronunciation some accent that is not one's native, because of the predictive processing of the brain. Our brains are constantly appropriating signals that are closely related to the known ones.

Is there a good bijection between specification gaming and wireheading vs different types of Goodhart's law?

What's a good way to force oneself outside their comfort zone where most expectations and intuitions routinely fail?

This might become useful to build antifragility about expectation management.

Quick example - living without money in a foreign nation.

Is it possible to design a personal or group retreat for this?

Where is the paradigm for Effective Activism? On a first thought, it doesn't even seem to be difficult to do better than status quo.

Sayan's Braindump

sayan

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

What is your Personal Knowledge Management system?

sayan

sayan, rosiecam

Personal knowledge management (PKM) is a collection of processes that a person uses to gather, classify, store, search, retrieve and share knowledge in their daily activities (Grundspenkis 2007) and the way in which these processes support work activities (Wright 2005). It is a response to the idea that knowledge workers need to be responsible for their own growth and learning (Smedley 2009). It is a bottom-up approach to knowledge management (KM) (Pollard 2008).

Wikipedia

I am curious about how LessWrongers manage personal information, including but not limited to - research reading/ research output, side-projects/ hobbies, blogging, managing watchlist/ to-read list, social information, incremental-reading, making flashcards, threads-from-unfinished-conversations, braindumps, and maybe even general GTD-stuff.

Information about any

... (read more)

Unknown Unknowns in AI Alignment

sayan

It seems to me that no matter how many problems from different research agendas we solve, there is always the possibility that some 'unknown unknown' misalignment scenario can occur. I can imagine an approach of building model-agnostic, environment-agnostic minimal assumption alignment guarantees (which seems to be super hard), but I feel like things can go wrong in myriad other ways, even then.

Has there been any discussion about how we might go about this?